{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:26:21Z","timestamp":1776885981819,"version":"3.51.2"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889709","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Why disentanglement-based speaker anonymization systems fail at preserving emotions?"],"prefix":"10.1109","author":[{"given":"\u00dcnal Ege","family":"Gaznepoglu","sequence":"first","affiliation":[{"name":"Friedrich-Alexander-University,International Audio Laboratories Erlangen,Erlangen-Nürnberg,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nils","family":"Peters","sequence":"additional","affiliation":[{"name":"Trinity College Dublin,Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"3rd VoicePrivacy challenge evaluation plan (version 2.0)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096607"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447871"},{"key":"ref4","article-title":"Anonymizing speech: Evaluating and designing speaker anonymization techniques","volume-title":"Ph.D. dissertation","author":"Champion","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2025.101810"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SPSC.2023-10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-448"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414913"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26479"},{"key":"ref10","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Trans. on Machine Learning Research (TMLR)"},{"key":"ref11","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. Intl. Conf. on Learning Representations (ICLR)","author":"Lee"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448436"},{"key":"ref13","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. Intl. Conf. on Machine Learning (ICML)","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref15","article-title":"We need variations in speech synthesis: Sub-center modelling for speaker embeddings","author":"Ulgen","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447060"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-191"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023234"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-39"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.2916590"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3313429"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-28"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref28","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"presented at the Proc. NeurIPS Conf","author":"Kong"},{"key":"ref29","volume-title":"Silero VAD: Pre-trained enterprise-grade voice activity detector (vad), number detector and language classifier","author":"Team","year":"2024"},{"key":"ref30","article-title":"Torchaudio.functional.loudness \u2014 torchaudio 2.3.0 documentation"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889709.pdf?arnumber=10889709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:25Z","timestamp":1774416265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889709\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889709","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}